Coding Agent
Kilo Code
Open-source coding agent for VS Code, JetBrains, and CLI
Our verdict
Open-source coding agent for VS Code, JetBrains, and CLI. 500+ models via Kilo Gateway. #2 on OpenRouter this week. Trusted at Meta, Amazon, and Airbnb.
Best for
Developers who want Claude Code-style agentic workflows but need JetBrains support or broader model access. The multi-IDE story is the clearest differentiator from Claude Code and Cursor.
Not for
Non-technical users wanting a no-code interface. Teams fully happy with Claude Code who don't need JetBrains or alternative model providers.
Overview
Kilo Code is an open-source AI coding agent — Apache-2.0 licensed — that runs across VS Code, JetBrains IDEs, and the CLI. It supports 500+ AI models via its Kilo Gateway, including BYOK for direct API access. Claimed to be the most popular open-source coding agent by downloads, with enterprise adoption at Meta, Amazon, and Airbnb. Cloud agents run 24/7 and integrate with Slack, Discord, and Telegram.
What works
- +VS Code, JetBrains, and CLI — the broadest IDE coverage of any coding agent on this list
- +500+ models via Kilo Gateway — not locked to Anthropic or OpenAI
- +Cloud agents run 24/7 without your laptop open
- +Apache-2.0 open source — auditable and self-hostable
- +Slack, Discord, and Telegram integrations for async agent workflows
- +Free tier with no credit card required
What doesn't
- −Newer than Cursor or Cline — smaller community, less battle-tested documentation
- −500+ model support adds decision overhead — more choices don't always mean better outcomes
- −Cloud agent feature is newer and less proven at scale than established CI/CD-based approaches
- −JetBrains support, while a key differentiator, lags VS Code in feature parity
What operators use it for
01
JetBrains Teams Who Want Agentic Coding
Cursor doesn't run in IntelliJ, WebStorm, or PyCharm. Kilo Code does. For teams invested in JetBrains IDEs who want the same agentic loop — read codebase, plan, edit across files, run tests — Kilo Code is the only serious option. The VS Code experience is good; the JetBrains experience fills a gap nobody else covers.
02
Model Flexibility Without Switching Tools
Kilo Gateway gives you 500+ models in one interface. Use Claude Sonnet for complex reasoning tasks, drop to a cheaper model for repetitive generation, switch to a local model for sensitive code. Same tool, same workflow, different models — without setting up separate API connections for each.
03
Async Agent Work via Slack or Discord
Trigger a Kilo Code agent from Slack, let it run overnight, get results in the channel when it finishes. The messaging integrations make it practical for teams that want agents doing work asynchronously — not just developers sitting in an IDE.
Pricing
Free tier available (Kilo Auto, no credit card required). Paid plans for higher usage. BYOK supported — connect your own API key to any of 500+ models via Kilo Gateway.
Continue exploring
Tool
AI Agent Cost Calculator
See what running Kilo Code's typical workflow costs at your volume — pre-filled for this category.
Tool
The AI Agent Picker
Not sure Kilo Code is right? Five questions, one recommendation.
Article
What Claude Skills actually are
Most builders think Skills are saved prompts. The architecture is different.
More in Coding agents
Claude Code
The next level up from the Claude you already use
Cursor
The AI-first IDE that 360k developers pay for
Aider
Open-source CLI pair programmer with model freedom
GitHub Copilot
The AI most developers already pay for, now with agent mode
Augment Code
The agentic coding tool built for large codebases
Amp
Sourcegraph's agentic coding tool with codebase context built in
OpenAI Codex
OpenAI's terminal-native coding agent
Cline
The open coding agent — 61k GitHub stars, 5M installs
Roo Code
Open-source VS Code agent with role-specific coding modes
OpenHands
The autonomous coding agent for full engineering tasks
Open dataset. This review is part of a structured dataset of every platform on the shortlist, published as platforms.json on GitHub under CC-BY-4.0.